Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to conditions or new rules affecting operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hurst
    -0.15
    ainter
    -0.15
    zel
    -0.14
    artic
    -0.14
     Reduction
    -0.13
    ETCH
    -0.13
    cq
    -0.13
    hear
    -0.13
    amin
    -0.13
    amy
    -0.13
    POSITIVE LOGITS
    ei
    0.17
    oÄŁ
    0.15
    uC
    0.14
    uja
    0.14
    elp
    0.14
    undler
    0.14
    oord
    0.13
     taper
    0.13
    fas
    0.13
     Budd
    0.13
    Act Density 0.548%

    No Known Activations